A method to learn high-performing and novel product layouts and its application to vehicle design

    Research output: Contribution to journalArticle

    3 Citations (Scopus)

    Abstract

    In this paper we aim at tackling the problem of searching for novel and high-performing product designs. Generally speaking, the conventional schemes usually optimize a (multi) objective function on a dynamic model/simulation, then perform a number of representative real-world experiments to validate and test the accuracy of the some product performance metric. However, in a number of scenarios involving complex product configuration, e.g. optimum vehicle design and large-scale spacecraft layout design, the conventional schemes using simulations and experiments are restrictive, inaccurate and expensive.In this paper, in order to guide/complement the conventional schemes, we propose a new approach to search for novel and high-performing product designs by optimizing not only a proposed novelty metric, but also a performance function which is learned from historical data. Rigorous computational experiments using more than twenty thousand vehicle models over the last thirty years and a relevant set of well-known gradient-free optimization algorithms shows the feasibility and usefulness to obtain novel and high performing vehicle layouts under tight and relaxed search scenarios.The promising results of the proposed method opens new possibilities to build unique and high-performing systems in a wider set of design engineering problems.

    Original languageEnglish
    JournalNeurocomputing
    DOIs
    Publication statusAccepted/In press - 2016 Jun 30

    Fingerprint

    Spacecraft
    Product design
    Experiments
    Dynamic models

    Keywords

    • Design
    • Genetic programming
    • Gradient-free optimization
    • Optimization
    • Vehicle

    ASJC Scopus subject areas

    • Computer Science Applications
    • Cognitive Neuroscience
    • Artificial Intelligence

    Cite this

    @article{3174d9bb083d43bfa5327c52eb40d7f9,
    title = "A method to learn high-performing and novel product layouts and its application to vehicle design",
    abstract = "In this paper we aim at tackling the problem of searching for novel and high-performing product designs. Generally speaking, the conventional schemes usually optimize a (multi) objective function on a dynamic model/simulation, then perform a number of representative real-world experiments to validate and test the accuracy of the some product performance metric. However, in a number of scenarios involving complex product configuration, e.g. optimum vehicle design and large-scale spacecraft layout design, the conventional schemes using simulations and experiments are restrictive, inaccurate and expensive.In this paper, in order to guide/complement the conventional schemes, we propose a new approach to search for novel and high-performing product designs by optimizing not only a proposed novelty metric, but also a performance function which is learned from historical data. Rigorous computational experiments using more than twenty thousand vehicle models over the last thirty years and a relevant set of well-known gradient-free optimization algorithms shows the feasibility and usefulness to obtain novel and high performing vehicle layouts under tight and relaxed search scenarios.The promising results of the proposed method opens new possibilities to build unique and high-performing systems in a wider set of design engineering problems.",
    keywords = "Design, Genetic programming, Gradient-free optimization, Optimization, Vehicle",
    author = "{Parque Tenorio}, Victor and Tomoyuki Miyashita",
    year = "2016",
    month = "6",
    day = "30",
    doi = "10.1016/j.neucom.2016.12.082",
    language = "English",
    journal = "Neurocomputing",
    issn = "0925-2312",
    publisher = "Elsevier",

    }

    TY - JOUR

    T1 - A method to learn high-performing and novel product layouts and its application to vehicle design

    AU - Parque Tenorio, Victor

    AU - Miyashita, Tomoyuki

    PY - 2016/6/30

    Y1 - 2016/6/30

    N2 - In this paper we aim at tackling the problem of searching for novel and high-performing product designs. Generally speaking, the conventional schemes usually optimize a (multi) objective function on a dynamic model/simulation, then perform a number of representative real-world experiments to validate and test the accuracy of the some product performance metric. However, in a number of scenarios involving complex product configuration, e.g. optimum vehicle design and large-scale spacecraft layout design, the conventional schemes using simulations and experiments are restrictive, inaccurate and expensive.In this paper, in order to guide/complement the conventional schemes, we propose a new approach to search for novel and high-performing product designs by optimizing not only a proposed novelty metric, but also a performance function which is learned from historical data. Rigorous computational experiments using more than twenty thousand vehicle models over the last thirty years and a relevant set of well-known gradient-free optimization algorithms shows the feasibility and usefulness to obtain novel and high performing vehicle layouts under tight and relaxed search scenarios.The promising results of the proposed method opens new possibilities to build unique and high-performing systems in a wider set of design engineering problems.

    AB - In this paper we aim at tackling the problem of searching for novel and high-performing product designs. Generally speaking, the conventional schemes usually optimize a (multi) objective function on a dynamic model/simulation, then perform a number of representative real-world experiments to validate and test the accuracy of the some product performance metric. However, in a number of scenarios involving complex product configuration, e.g. optimum vehicle design and large-scale spacecraft layout design, the conventional schemes using simulations and experiments are restrictive, inaccurate and expensive.In this paper, in order to guide/complement the conventional schemes, we propose a new approach to search for novel and high-performing product designs by optimizing not only a proposed novelty metric, but also a performance function which is learned from historical data. Rigorous computational experiments using more than twenty thousand vehicle models over the last thirty years and a relevant set of well-known gradient-free optimization algorithms shows the feasibility and usefulness to obtain novel and high performing vehicle layouts under tight and relaxed search scenarios.The promising results of the proposed method opens new possibilities to build unique and high-performing systems in a wider set of design engineering problems.

    KW - Design

    KW - Genetic programming

    KW - Gradient-free optimization

    KW - Optimization

    KW - Vehicle

    UR - http://www.scopus.com/inward/record.url?scp=85015788820&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85015788820&partnerID=8YFLogxK

    U2 - 10.1016/j.neucom.2016.12.082

    DO - 10.1016/j.neucom.2016.12.082

    M3 - Article

    AN - SCOPUS:85015788820

    JO - Neurocomputing

    JF - Neurocomputing

    SN - 0925-2312

    ER -